Towards training Bilingual and Code-Switched Speech Recognition models from Monolingual data sources.
Kunal DhawanDima RekeshBoris GinsburgPublished in: CoRR (2023)
Keyphrases
- speech recognition
- acoustic models
- hidden markov models
- data sources
- language model
- machine translation
- speech recognizer
- wall street journal corpus
- speech processing
- automatic speech recognition
- speech retrieval
- speech recognition systems
- speech signal
- image processing
- isolated word
- speech recognition technology
- pattern recognition
- cross lingual
- training process
- speech recognizers
- probabilistic model
- speaker independent
- question answering
- speech synthesis
- cross language
- query translation
- discriminative training
- natural language processing
- speaker dependent
- relevance feedback
- speaker identification
- noisy environments
- information retrieval